Local embedder and reranker for Eidentic — run bge-small-en-v1.5 and cross-encoder reranking via @huggingface/transformers, no API key required.

> **Status: Foundation** — The zero-config in-memory RAG path and tool factory are real; persistent pgvector storage and provider-grade reranking remain adapter-owned gaps.

Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking

🏠 Local AI provider for FlowRAG - ONNX embeddings and reranking, fully offline

Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking

An MCP server for Jina AI, providing tools for embeddings, reranking, and generation. NodeJS Version.

Query Source Code - AST-based code search with hybrid BM25+Vector+LLM reranking

Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking

🎭 Anthropic provider for FlowRAG - entity extraction and reranking via Claude

Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking

Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking. Customized fork of tobi/qmd.

Turn any web article into a queryable MCP server. SQLite + FTS5 + optional local embeddings and cross-encoder reranking.

A lightweight package providing information about various Large Language Models (LLMs), including embedding, reranking, and other models.

AsterMind Community - Complete ELM library with 21+ advanced variants, Pro features (RAG, reranking, summarization), and OmegaSynth synthetic data generation. Free and open-source. Combines all features from AsterMind-ELM, AsterMind-Pro, AsterMind-Premium

Adaptive retrieval orchestration for RAG and semantic search in TypeScript: per-query routing across vector / BM25 / hybrid + cross-encoder reranking, with full traces. Works with pgvector, Pinecone, Turbopuffer, or any custom adapter.

QKB - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking

Semantic code search CLI for Jira tasks — AST-level indexing, vector search, cross-encoder reranking, repomix XML output

AI-powered intelligent code search with LLM reranking - MCP server for Claude, Cursor, Cline

Private web search MCP server for Claude Code, LibreChat, OpenCode — powered by SearXNG with local ML reranking, SSRF-safe fetch, and optional vector search.

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level